Springboot集成tess4j实现OCR图片文字识别

识别率在90%以上

1. 集成pom

        <dependency>
            <groupId>net.sourceforge.tess4j</groupId>
            <artifactId>tess4j</artifactId>
            <version>4.5.4</version>
        </dependency>

2. 训练好的语言文件
   https://gitcode.com/tesseract-ocr/tessdata/tree/main
3. 代码

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.springframework.stereotype.Service;

import java.io.File;
import java.io.InputStream;
import java.net.URL;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.nio.file.StandardCopyOption;

@Service
public class OcrService {

    public String recognizeText(File imageFile) throws TesseractException {
        Tesseract tesseract = new Tesseract();
        // 设定训练文件的位置
        tesseract.setDatapath("D:\\xxxxx\\tessdata");
        // 指定识别类型
        tesseract.setLanguage("chi_sim");
        return tesseract.doOCR(imageFile);
    }

    public String recognizeTextFromUrl(String imageUrl) throws Exception {
        URL url = new URL(imageUrl);
        InputStream in = url.openStream();
        Files.copy(in, Paths.get("downloaded.jpg"), StandardCopyOption.REPLACE_EXISTING);

        File imageFile = new File("downloaded.jpg");
        return recognizeText(imageFile);
    }
}

import org.springframework.http.ResponseEntity;
import org.springframework.web.bind.annotation.*;
import org.springframework.web.multipart.MultipartFile;

import java.io.File;

@RestController
@RequestMapping("/api/ocr")
public class OcrController {

    private final OcrService ocrService;

    // 使用构造器注入OcrService
    public OcrController(OcrService ocrService) {
        this.ocrService = ocrService;
    }

    @PostMapping("/upload")
    public ResponseEntity<String> uploadImage(@RequestParam("file") MultipartFile file) {
        try {
            File convFile = new File(System.getProperty("java.io.tmpdir")+"/"+file.getOriginalFilename());
            file.transferTo(convFile);
            String result = ocrService.recognizeText(convFile);
            return ResponseEntity.ok(result);
        } catch (Exception e) {
            e.printStackTrace();
            return ResponseEntity.badRequest().body("识别发生错误：" + e.getMessage());
        }
    }

    @GetMapping("/recognize-url")
    public ResponseEntity<String> recognizeFromUrl(@RequestParam("imageUrl") String imageUrl) {
        try {
            String result = ocrService.recognizeTextFromUrl(imageUrl);
            return ResponseEntity.ok(result);
        } catch (Exception e) {
            e.printStackTrace();
            return ResponseEntity.badRequest().body("从URL识别发生错误：" + e.getMessage());
        }
    }
}

4. 结果